Inflammatory subgroups of schizophrenia and their association with brain structure: A semi-supervised machine learning examination of heterogeneity

Paris Alexandros Lalousis*, Lianne Schmaal, Stephen Wood, Renate Reniers, Vanessa L Cropley, Andrew Watson, Christos Pantelis, John Suckling, Nicholas Barnes, Carmine M. Pariante, P Jones, Eileen Joyce, Thomas RE Barnes, SM Lawrie, Nusrat Husain, Paola Dazzan, Bill Deakin, Cynthia S Weickert, Rachel Upthegrove

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

39 Downloads (Pure)

Abstract

Objective: Immune system dysfunction is hypothesised to contribute to structural brain changes through aberrant synaptic pruning in schizophrenia. However, evidence is mixed and there is a lack of evidence of inflammation and its effect on grey matter volume (GMV) in patients. We hypothesised that inflammatory subgroups can be identified and that the subgroups will show distinct neuroanatomical and neurocognitive profiles.

Methods: The total sample consisted of 1067 participants (chronic patients with schizophrenia n=467 and healthy controls (HCs) n=600) from the Australia Schizophrenia Research Bank (ASRB) dataset, together with 218 recent-onset patients with schizophrenia from the external Benefit of Minocycline on Negative Symptoms of Psychosis: Extent and Mechanism (BeneMin) dataset. HYDRA (HeterogeneitY through DiscRiminant Analysis) was used to separate schizophrenia from HC and define disease-related subgroups based on inflammatory markers. Voxel-based morphometry and inferential statistics were used to explore GMV alterations and neurocognitive deficits in these subgroups.

Results: An optimal clustering solution revealed five main schizophrenia groups separable from HC: Low Inflammation, Elevated CRP, Elevated IL-6/IL-8, Elevated IFN-γ, and Elevated IL-10 with an adjusted Rand index of 0.573. When compared with the healthy controls, the IL-6/IL-8 cluster showed the most widespread, including the anterior cingulate, GMV reduction. The IFN-γ inflammation cluster showed the least GMV reduction and impairment of cognitive performance. The CRP and the Low Inflammation clusters dominated in the younger external dataset.

Conclusions: Inflammation in schizophrenia may not be merely a case of low vs high, but rather there are pluripotent, heterogeneous mechanisms at play which could be reliably identified based on accessible, peripheral measures. This could inform the successful development of targeted interventions.
Original languageEnglish
Pages (from-to)166-175
JournalBrain, Behavior, and Immunity
Volume113
Early online date7 Jul 2023
DOIs
Publication statusPublished - 1 Oct 2023

Keywords

  • Inflammation
  • Schizophrenia
  • MRI
  • Machine learning

Fingerprint

Dive into the research topics of 'Inflammatory subgroups of schizophrenia and their association with brain structure: A semi-supervised machine learning examination of heterogeneity'. Together they form a unique fingerprint.

Cite this